Boosting Poisson Regression Models with Telematics Car Driving Data

25 Pages Posted: 4 Jun 2020

See all articles by Guangyuan Gao

Guangyuan Gao

Renmin University of China - School of Statistics

He Wang

affiliation not provided to SSRN

Mario V. Wuthrich

RiskLab, ETH Zurich

Date Written: May 8, 2020

Abstract

With the emergence of telematics car driving data, insurance companies start to boost classical actuarial regression models for claim frequency prediction. In this paper, we propose two data-driven neural network approaches that process telematics car driving data to construct driving behavior risk factors. Neural networks simultaneously accommodate feature engineering and regression modeling. We conclude in our numerical analysis that both classical actuarial risk factors and telematics car driving data is necessary to receive the best predictive models. This indicates that these two sources of information interact and complement each other.

Keywords: Densely connected neural network, Convolutional neural network, Combined actuarial neural network, Claims frequency modeling, Telematics car driving data, Poisson regression, Generalized linear model, Regression tree, Telematics heatmap

JEL Classification: G22, C23, C45, C51

Suggested Citation

Gao, Guangyuan and Wang, He and Wuthrich, Mario V., Boosting Poisson Regression Models with Telematics Car Driving Data (May 8, 2020). Available at SSRN: https://ssrn.com/abstract=3596034 or http://dx.doi.org/10.2139/ssrn.3596034

Guangyuan Gao

Renmin University of China - School of Statistics ( email )

No.59 Zhongguancun Street, Renmin University
Beijing, 100872
China

He Wang

affiliation not provided to SSRN

Mario V. Wuthrich (Contact Author)

RiskLab, ETH Zurich ( email )

Department of Mathematics
Ramistrasse 101
Zurich, 8092
Switzerland

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
112
Abstract Views
566
rank
272,801
PlumX Metrics